Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1877 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0705. Min Act: -0.0002

Data Index: 1585087 (Python Code)

Max Activating Token Index: 376

Text #1

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0696. Min Act: -0.0003

Data Index: 866462 (C4 (Web Text))

Max Activating Token Index: 164

Text #2

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0687. Min Act: -0.0003

Data Index: 1377152 (Python Code)

Max Activating Token Index: 744

Text #3

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0660. Min Act: -0.0004

Data Index: 217228 (C4 (Web Text))

Max Activating Token Index: 856

Text #4

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0664. Min Act: -0.0003

Data Index: 1571177 (Python Code)

Max Activating Token Index: 83

Text #5

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0646. Min Act: -0.0004

Data Index: 1205780 (C4 (Web Text))

Max Activating Token Index: 28

Text #6

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0631. Min Act: -0.0003

Data Index: 437556 (C4 (Web Text))

Max Activating Token Index: 453

Text #7

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0623. Min Act: -0.0004

Data Index: 197217 (C4 (Web Text))

Max Activating Token Index: 331

Text #8

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0628. Min Act: -0.0003

Data Index: 294194 (C4 (Web Text))

Max Activating Token Index: 440

Text #9

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0605. Min Act: -0.0003

Data Index: 659682 (C4 (Web Text))

Max Activating Token Index: 737

Text #10

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0582. Min Act: -0.0003

Data Index: 550344 (C4 (Web Text))

Max Activating Token Index: 821

Text #11

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0609. Min Act: -0.0003

Data Index: 1632711 (Python Code)

Max Activating Token Index: 834

Text #12

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0608. Min Act: -0.0003

Data Index: 1244751 (C4 (Web Text))

Max Activating Token Index: 177

Text #13

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0590. Min Act: -0.0003

Data Index: 487673 (C4 (Web Text))

Max Activating Token Index: 962

Text #14

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0573. Min Act: -0.0003

Data Index: 841227 (C4 (Web Text))

Max Activating Token Index: 194

Text #15

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0574. Min Act: -0.0002

Data Index: 1519345 (Python Code)

Max Activating Token Index: 341

Text #16

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0560. Min Act: -0.0003

Data Index: 1542171 (Python Code)

Max Activating Token Index: 975

Text #17

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0568. Min Act: -0.0003

Data Index: 60711 (C4 (Web Text))

Max Activating Token Index: 270

Text #18

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0559. Min Act: -0.0003

Data Index: 1443325 (Python Code)

Max Activating Token Index: 979

Text #19

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0567. Min Act: -0.0003

Data Index: 1340519 (C4 (Web Text))

Max Activating Token Index: 218